ABSTRACT
We propose a software pipeline to generate 3D animations by using the motion capture (mocap) data and human shape models. The proposed pipeline integrates two animation software tools, Maya and MotionBuilder in one flow. Specifically, we address the issue of skeleton incompatibility among the mocap data, shape models, and animation software. Our objective is to generate both realistic and accurate motion-specific animation sequences. Our method is tested by three mocap data sets of various motion types and five commercial human shape models, and it demonstrates better visual realisticness and kinematic accuracy when compared with three other animation generation methods.
- CMU Mocap Library. http://mocap.cs.cmu.edu/.Google Scholar
- Ohio State University Motion Capture Lab. http://accad.osu.edu/research/mocap/mocapdata.htm.Google Scholar
- A. Agarwal and B. Triggs. 3D human pose from silhouettes by relevance vector regression. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2004. Google ScholarDigital Library
- I. Baran and J. Popovic. Automatic rigging and animation of 3D characters. ACM Trans. on Graphics, 26, 2007. Google ScholarDigital Library
- J. Black, T. Ellis, and P. Rosin. A novel method for video tracking performance evaluation. In Proc. VS-PETS, 2003.Google Scholar
- C. Canton-Ferrer, J. Casas, and M. Pardas. Exploiting structural hierarchy in articulated objects towards robust motion capture. In Conf. on Articulated Motion and Deformable Objects, 2008. Google ScholarDigital Library
- Y. Chen, R. Parent, R. Machiraju, and J. Davis. Human activity recognition for synthesis. In IEEE Workshop on Learning, Representation, and Context for Human Sensing in Video, 2006.Google Scholar
- Z. Deng, Q. Gu, and Q. Li. Perceptually consistent example-based human motion retrieval. In Proc. of ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (SI3D), 2009. Google ScholarDigital Library
- X. Desurmont, J.-B. Hayet, C. Machy, J.-F. Delaigle, and J.-F. Macq. On the performance evaluation of tracking systems using multiple pan-tilt-zoom cameras. In IS&T/SPIE Symposium on Electronic Imaging, 2007.Google Scholar
- A. Elgammal and C.-S. Lee. Tracking people on torus. IEEE Trans. on Pattern Analysis and Machine Intelligence, 31:520--538, 2009. Google ScholarDigital Library
- M. Gleicher. Retargetting motion to new characters. In SIGGRAPH, 1998. Google ScholarDigital Library
- A. Godil and S. Ressler. Retrieval and clustering from a 3d human database based on body and head shape. In Proc. of SAE Digital Human Modeling Conference, 2006.Google ScholarCross Ref
- F. Guo and G. Qian. Monocular 3D tracking of articulated human motion in silhouette and pose manifolds. EURASIP Journal on Image and Video Processing, 2008:1--18, 2008. Google ScholarDigital Library
- L. Kovar, M. Gleicher, and F. Pighin. Motion graphs. In SIGGRAPH '08: ACM SIGGRAPH 2008 classes, pages 1--10, New York, NY, USA, 2008. ACM. Google ScholarDigital Library
- Y. Li, B. Wu, and R. Nevatia. Human detection by searching in 3d space using camera and scene knowledge. In Proc. International Conference on Pattern Recognition, 2008.Google ScholarCross Ref
- Z. Lin, L. S. Davis, D. Doermann, and D. DeMenthon. Hierarchical part-template matching for human detection and segmentation. In IEEE International Conference on Computer Vision, 2007.Google ScholarCross Ref
- M. Meredith and S. Maddock. Motion capture file formats explained. Technical Report CS-01-11, University of Sheffield.Google Scholar
- M. Müller, T. Röder, and M. Clausen. Efficient content-based retrieval of motion capture data. ACM Trans. Graph., 24(3):677--685, 2005. Google ScholarDigital Library
- L. Mundermann, S. Corazza, and T. P. Andriacchi. Accurately measuring human movement using articulated ICP with soft-joint constraints and a repository of articulated models. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2007.Google ScholarCross Ref
- O. Onder, U. Gudukbay, B. Ozguc, T. Erdem, C. E. Erdem, and M. Ozkan. Keyframe reduction techniques for motion capture data. In Proceedings of the 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video, 2008.Google ScholarCross Ref
- J. Park, S. Park, and J. Aggarwal. Model-based human motion tracking and behavior recognition using hierarchical finite state automata. In ACM Conference on Image and Video Retrieval, 2003.Google ScholarCross Ref
- M. Pawar, G. Pradhan, K. Zhang, and B. Prabhakaran. Content based querying and searching for 3D human motions. In Proc. of Internaltional ACM Multimedia Modeling Conference, 2008. Google ScholarDigital Library
- B. Peng, G. Qian, and S. Rajko. View-invariant full-body gesture recognition from video. In Proc. of International Conference on Pattern Recognition, 2008.Google ScholarCross Ref
- F. Qureshi and D. Terzopoulos. Towards intelligent camera networks: A virtual vision approach. In Proc. VS-PETS, 2005.Google ScholarCross Ref
- H. Ragheb, S. Velastin, P. Remagnino, and T. Ellis. Vihasi: Virtual human action silhouette data for the performance evaluation of silhouette-based action recognition methods. In Workshop on Activity Monitoring by Multi-Camera Surveillance Systems, 2008.Google ScholarDigital Library
- L. Ren, A. Patrick, A. A. Efros, J. K. Hodgins, and J. M. Rehg. A data-driven approach to quantifying natural human motion. ACM Transactions on Graphics (SIGGRAPH 2005), 24(3):1090--1097, Aug. 2005. Google ScholarDigital Library
- T. Schlogl, C. Beleznai, M. Winter, and H. Bischof. Performance evaluation metrics for motion detection and tracking. In Procs. International Conference on Pattern Recognition, 2004. Google ScholarDigital Library
- G. Shakhnarovich, P. Viola, and T. Darrell. Fast pose estimation with parameter sensitive hashing. In Proc. of International Conference on Computer Vision, 2003. Google ScholarDigital Library
- L. Sigal, S. Bhatia, S. Roth, M. Black, and M. Isard. Tracking loose-limbed people. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2004.Google ScholarCross Ref
- L. Sigal and M. Black. HumanEva: Synchronized video and motion capture dataset for evaluation of articulated human motion. Technical Report CS-06-08, Brown University, 2006.Google Scholar
- C. Sminchisescu, A. Kanaujia, and D. N. Metaxas. Bm3e: Discriminative density propagation for visual tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence, 29:2030--2044, 2007. Google ScholarDigital Library
- C. Sminchisescu and B. Triggs. Kinematic jump processes for monocular 3d human tracking. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2003. Google ScholarDigital Library
- G. R. Taylor, A. J. Chosak, and P. C. Brewer. OVVV: Using virtual worlds to design and evaluate surveillance systems. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2007.Google ScholarCross Ref
- R. Urtasun and P. Fua. 3d human body tracking using deterministic temporal motion models. In Proc. of European Conference on Computer Vision, 2004.Google ScholarCross Ref
- X. K. Wei and J. Chai. Modeling 3d human poses from uncalibrated monocular images. In Proc. IEEE International Conference on Computer Vision, 2009.Google ScholarCross Ref
- X. Zhang and G. Fan. Dual gait generative models for human motion estimation from a single camera. IEEE Trans. on Systems, Man, and Cybernetics Part B: Cybernetics, 2010 (to appear). Google ScholarDigital Library
- X. Zhang, G. Fan, and L. Chou. Two-layer gait generative models for estimating unknown human gait kinematics. In Proc. IEEE ICCV Workshop on Machine Learning for Vision-based Motion Analysis, 2009.Google Scholar
Index Terms
- A software pipeline for 3D animation generation using mocap data and commercial shape models
Recommendations
Interactive manipulation of large-scale crowd animation
Editing large-scale crowd animation is a daunting task due to the lack of an efficient manipulation method. This paper presents a novel cage-based editing method for large-scale crowd animation. The cage encloses animated characters and supports ...
Synchronized multi-character motion editing
The ability to interactively edit human motion data is essential for character animation. We present a novel motion editing technique that allows the user to manipulate synchronized multiple character motions interactively. Our Laplacian motion editing ...
Mobilizing mocap, motion blending, and mayhem: rig interoperability for crowd simulation on Incredibles 2
SIGGRAPH '18: ACM SIGGRAPH 2018 TalksThe stylized world of Incredibles 2 features large urban crowds both in everyday situations and in scenes of panicked mayhem. While Pixar's now academy award winning animation software, Presto, has allowed us to create expressive and nuanced rigs for ...
Comments